© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14126
    Prev
    Next
    INDEX
    Explanations

    saving python code as .py files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Detox
    0.74
     devenue
    0.70
    逹
    0.69
    }^{(
    0.68
    들도
    0.66
    들을
    0.66
    ন্ড
    0.66
    illance
    0.64
    }^{\
    0.64
     Achieving
    0.64
    POSITIVE LOGITS
     somewhere
    0.71
    aturamento
    0.69
    ipes
    0.68
    Then
    0.67
    。
    0.67
    在一个
    0.66
    any
    0.66
    你可以
    0.66
    aan
    0.65
    onto
    0.65
    Activations Density 0.011%

    No Known Activations